Addressing Annotation Scarcity in Hyperspectral Brain Image Segmentation With Unsupervised Domain Adaptation
MCML Authors
Daniel Rückert
Prof. Dr.
Director
Abstract
Daniel Rückert
Prof. Dr.
Director
Abstract
This work presents a novel deep learning framework for segmenting cerebral vasculature in hyperspectral brain images. We address the critical challenge of severe label scarcity, which impedes conventional supervised training. Our approach utilizes a novel unsupervised domain adaptation methodology, using a small, expert-annotated ground truth alongside unlabeled data. Quantitative and qualitative evaluations confirm that our method significantly outperforms existing state-of-the-art approaches, demonstrating the efficacy of domain adaptation for label-scarce biomedical imaging tasks.
misc
Preprint
Aug. 2025Authors
T. Mach • D. Rückert • A. Berger • L. Lux • I. EzhovLinks
Research Area
BibTeXKey: MRB+25